arXiv Computer Vision

Stable and Scalable Bundle Adjustment of Holistic 3D Structures

The paper introduces a unified bundle adjustment framework that jointly optimizes camera parameters, sparse 3D points, and richer geometric features such as lines, coplanarity, and parallelism. It classifies features into scalable ones with direct 2D measurements and higher‑order groups that can be treated as camera‑like entities, allowing group constraints and cross‑feature relations to be expressed via 2D reprojection errors. This approach preserves the sparsity of classical point‑based BA, maintains numerical stability, and achieves runtime comparable to point‑only BA while producing richer 3D structures and improved accuracy.

arXiv Computer Vision
Sep 3

Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models

The paper introduces Self-Geometry, a plug‑and‑play test‑time adaptation framework that enforces explicit multi‑view geometric constraints on Vision Foundation Models (VFMs) using 2D pixel correspondences as pseudo ground truth. It combines Geometric Disentanglement Optimization—mixing Multi‑View and Epipolar Consistency losses with Gradient Disentanglement—to avoid gradient conflicts, a Frame Angular‑Neighbor sampler based on SO(3) geodesic distances to select informative views, and a Lightweight TTA module that adapts VFMs via LoRA. Experiments on six VFMs and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom) show consistent improvements in pose and geometry estimation.

By Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae, Jihyong Oh
arXiv Computer Vision
Sep 3

PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting

PointGauss is a 3D-native framework that performs semantic parsing and instance segmentation on 3D Gaussian splatting representations by treating Gaussian primitives as unstructured point sets and extracting scale‑invariant geometric features with Point Transformer V3. It introduces an adaptive region‑of‑interest cropping strategy and an instance‑aware distance‑constrained rasterization pipeline to enable scalable, view‑consistent pixel‑level projections. The authors also release SplatSeg‑360, a cross‑scale benchmark with 32 complex scenes and over 6,300 aligned 2D‑3D masks, and show that PointGauss achieves real‑time performance with state‑of‑the‑art 3D‑mIoU (~90%) and 2D‑mIoU (~80%) scores.

By Wentao Sun, Yiping Chen, John S. Zelek, Jonathan Li
arXiv Computer Vision
Sep 7

HiSfM: Disambiguating Structure-from-Motion via Scaffold-Anchored Hierarchical Reconstruction

HiSfM introduces a hierarchical coarse‑to‑fine Structure‑from‑Motion framework that enhances robustness and efficiency by building a scaffold of local communities and a compact skeleton using edge‑disjoint spanning trees. The method verifies skeletal edges with a two‑view disambiguator, constructs a stable scaffold as an anchor, and then registers remaining images for refinement. Experiments on ambiguity‑focused benchmarks and general datasets demonstrate that HiSfM avoids ambiguity‑induced failures, reduces runtime, and improves completeness compared to prior approaches.

By Ziding Zhao, Hainan Cui, Peilin Tao, Shuhan Shen
Hugging Face Trending Papers
Aug 11

CasDeblurGS: Cascaded 2D-to-3D Multi-View Consistency for 3D Gaussian Splatting from Two Blurry Images

Free-viewpoint 3D scene media is increasingly important for immersive applications, yet practical capture often suffers from severe view sparsity and motion blur. Although neural rendering has advanced sparse-view synthesis, existing blur-aware methods typically require substantial multi-view redundancy, accurate camera poses, or costly per-scene optimization.

arXiv Computer Vision
Sep 7

BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priors

BLASt3R presents a regularized bundle adjustment framework that combines a fast multi‑view matcher with monocular priors for initialization and regularization. The method unifies online Visual SLAM and offline reconstruction from unordered image collections, using a single optimization pipeline and shared hyperparameters. Experiments show that BLASt3R improves performance and speed tradeoffs compared to traditional, feed‑forward, and hybrid baselines, and its uncalibrated VSLAM variant surpasses all previous calibrated approaches.

By Vincent Leroy, Philippe Weinzaepfel, Lojze Zust, Yohann Cabon, J\'erome Revaud
arXiv Computer Vision
Sep 4

STARS-GS: Structure-Aware Regularized Gaussian Splatting for Large-Scale Aerial Surface Reconstruction

STARS-GS is a new structure‑aware 3D Gaussian Splatting framework designed for large‑scale aerial surface reconstruction. It introduces a scene partitioning strategy that preserves continuous scene elements, a neighborhood‑aware Gaussian organization that extends geometric constraints to local neighborhoods, and an adaptive surface regularization that tailors regularization strength to local geometry. Experiments on aerial photogrammetry benchmarks show that STARS‑GS improves the average F1‑score from 0.640 to 0.698, a relative gain of about 9.1%.

By Bocheng Li, Wenjuan Zhang, Jie Pan. Dongxu Han, Xuesong Ma, Yiling Yao, Yaning Wang
arXiv Computer Vision
Sep 3

Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning

The paper introduces a generalizable deformation learning framework that reconstructs 3D objects by deforming a category-level shape template to match a monocular observation. It employs a geometry-guided feature modeling mechanism to enrich foundation features with template topology, creating a geometry-aware representation that is explicitly correlated with the target observation for precise deformation. A view-adaptive feature aggregation module further bridges the gap between the fixed template and arbitrary target views by leveraging multi-view template features and camera poses, ensuring robust feature alignment across diverse viewpoints.

By Yiyao Ma, Kai Chen, Zhongxiang Zhou, Zhuheng Song, Dongsheng Xie, Zelong Tan, Rong Xiong, Qi Dou